© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 97760
    Prev
    Next
    INDEX
    Explanations

    multiple languages and programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    een
    -0.08
    ox
    -0.07
     allá
    -0.07
    Ot
    -0.07
     zusammen
    -0.07
    ot
    -0.07
    lopen
    -0.07
     sammen
    -0.07
    ൾ
    -0.07
    afet
    -0.06
    POSITIVE LOGITS
    ond
    0.11
    ONDS
    0.11
    onds
    0.10
    OND
    0.10
    ంధ
    0.10
    न्ध
    0.10
    ונד
    0.10
    earing
    0.10
    ondra
    0.09
    irthday
    0.09
    Activations Density 0.028%

    No Known Activations